Transformer block拆解

• Transformer block拆解
  • 基本结构
  • Zoom in Feed Forward子模块
  • 典型模型基本参数
  • References

基本结构

basic参数

• or : total number of transformer blocks

• or : number of units in each bottleneck layer, and number of units of each Q/K/V input

• or : number of heads of each transformer block

• or : input sequence length

derived参数

• : dimension of each attention head,

• : intermediate layer units of feed forward layer,

各参数在transformer block中的详细示意图如下(可双击放大)：

Zoom in Feed Forward子模块

典型模型基本参数

应用	模型
NLP	GPT-3	96	12288	96	2048
NLP	BERT_Base	12	768	12	128/512
NLP	BERT_Large	24	1024	16	128/512
RecSys	BST	1	128(max)	8	20

• BST: Behavior Sequence Transformer

References

1. The GPT-3 Architecture, on a Napkin

2. GPT-3 An Overview

3. Language Models are Few-Shot Learners

4. Improving Language Understanding by Generative Pre-Training

5. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

6. Attention Is All You Need

7. BERT transformer block code

8. Deep Learning Recommendation Model for Personalization and Recommendation Systems

9. Behavior Sequence Transformer for E-commerce Recommendation in Alibaba